Temporal Behavioral Parameters of On-Going Gaze Encounters in a Virtual Environment

Hartz, Arne; Guth, Björn; Jording, Mathis; Vogeley, Kai; Schulte‐Rüther, Martin

doi:10.3389/fpsyg.2021.673982

Cited by 8 publications

(8 citation statements)

References 68 publications

(88 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its validity, however, depends on the expertise and experience of the observer (Kamp‐Becker et al., 2018). Future developments should incorporate quantifiable indices of behavior, for example, eye gaze (Chong et al., 2019; Hartz, Guth, Jording, Vogeley, & Schulte‐Rüther, 2021), facial expression (Drimalla et al., 2020), motion (Budman et al., 2019), or even neural assessment during social interaction (Kruppa et al., 2020). A holistic approach is necessary (Roessner et al., 2021), including intermediate steps: Future studies could aim to set up generative models that describe how quantifiable behavioral indices translate into clinician symptom ratings, and in a second step, relate these to the diagnostic classification.…”

Section: Discussionmentioning

confidence: 99%

Using machine learning to improve diagnostic assessment of ASD in the light of specific differential and co‐occurring diagnoses

Schulte‐Rüther

Kulvičius

Stroth

et al. 2022

Child Psychology Psychiatry

View full text Add to dashboard Cite

Background: Diagnostic assessment of ASD requires substantial clinical experience and is particularly difficult in the context of other disorders with behavioral symptoms in the domain of social interaction and communication. Observation measures such as the Autism Diagnostic Observation Schedule (ADOS) do not take into account such co-occurring disorders. Method: We used a well-characterized clinical sample of individuals (n = 1,251) that had received detailed outpatient evaluation for the presence of an ASD diagnosis (n = 481) and covered a range of additional overlapping diagnoses, including anxiety-related disorders (ANX, n = 122), ADHD (n = 439), and conduct disorder (CD, n = 194). We focused on ADOS module 3, covering the age range with particular high prevalence of such differential diagnoses. We used machine learning (ML) and trained random forest models on ADOS single item scores to predict a clinical best-estimate diagnosis of ASD in the context of these differential diagnoses (ASD vs. ANX, ASD vs. ADHD, ASD vs. CD), in the context of co-occurring ADHD, and an unspecific model using all available data. We employed nested cross-validation for an unbiased estimate of classification performance and made available a Webapp to showcase the results and feasibility for translation into clinical practice. Results: We obtained very good overall sensitivity (0.89-0.94) and specificity (0.87-0.89). In particular for individuals with less severe symptoms, our models showed increases of up to 35% in sensitivity or specificity. Furthermore, we analyzed item importance profiles of the ANX, ADHD, and CD models in comparison with the unspecific model revealing distinct patterns of importance for specific ADOS items with respect to differential diagnoses. Conclusions: ML-based diagnostic classification may improve clinical decisions by utilizing the full range of information from detailed diagnostic observation instruments such as the ADOS. Importantly, this strategy might be of particular relevance for older children with less severe symptoms for whom the diagnostic decision is often particularly difficult.

show abstract

Section: Discussionmentioning

confidence: 99%

Using machine learning to improve diagnostic assessment of ASD in the light of specific differential and co‐occurring diagnoses

Schulte‐Rüther

Kulvičius

Stroth

et al. 2022

Child Psychology Psychiatry

View full text Add to dashboard Cite

show abstract

“…On each block, the face of a human avatar was continuously displayed on the screen. We used DAZ Studio 4.9 (DAZ Productions, Inc., USA) to create a modified version of the stimuli validated by Hartz et al (2021). Eleven pictures of the avatar with different levels of smiling were created for the visualization of the feedback signal.…”

Section: Methodsmentioning

confidence: 99%

Section: Neurofeedback Trainingmentioning

confidence: 99%

Successful Modulation of Temporoparietal Junction Activity and Stimulus-Driven Attention by fNIRS-based Neurofeedback – a Randomized Controlled Proof-of-Concept Study

Mehlis

Uttecht

Lührs

et al. 2023

Preprint

View full text Add to dashboard Cite

The right temporoparietal junction (rTPJ) is a core hub in neural networks associated with reorienting of attention and social cognition. However, it remains unknown whether participants can learn to actively modulate their rTPJ activity via neurofeedback. Here, we explored the feasibility of functional near-infrared spectroscopy (fNIRS)-based neurofeedback in modulating rTPJ activity and its effect on rTPJ functions such as reorienting of attention and visual perspective taking. In a bidirectional regulation control group design, 50 healthy participants were either reinforced to up- or downregulate rTPJ activation over four days of training. Both groups showed a spontaneous increase in rTPJ activity (upregulation effect), but only the upregulation group maintained this effect, while the downregulation group showed a decline from the initial rTPJ activation. This suggests a successful upregulation in the upregulation group and a learning effect in the downregulation group only. We found a significant group x time interaction effect in the performance of the reorienting of attention task and group-specific changes, with decreased reaction times (RTs) in the upregulation group and increased RTs in the downregulation group across all conditions after neurofeedback training. Those with low baseline performance showed greater improvements. In the perspective-taking task, however, only time effects were observed that were non-group-specific. These findings demonstrate that fNIRS-based neurofeedback is a feasible method to modulate rTPJ functions with evidence of neurophysiologically specific effects, thus paving the way for future applications of non-invasive rTPJ modulation in neuropsychiatric disorders.

show abstract

“…More quantifiable indices of behavior derived from an ADOS-like examination would be desirable to allow for a more precise and observerindependent assessment. Future developments should incorporate quantifiable assessments of eye gaze (Chong et al, 2019;Hartz et al, 2021), facial expression (Drimalla et al, 2020), motion (Budman et al, 2019), or even neural assessment during social interaction (Kruppa et al, 2020). However, it is unlikely that machine learning approaches will succeed in directly relating the basic building blocks of interactive social behavior to a clinical diagnosis of a heterogeneous disorder such as ASD.…”

Section: Future Directionsmentioning

confidence: 99%

Using machine learning to improve diagnostic assessment of ASD in the light of specific differential diagnosis

Schulte‐Rüther

Kulvičius

Stroth

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

BackgroundDiagnostic assessment of ASD requires substantial clinical experience and is particular difficult in the context of other disorders with behavioral symptoms in the domain of social interaction and communication. Observation measures such as the Autism Diagnostic Observation Schedule (ADOS) do not take into account such comorbid and differential disorders.MethodWe used a well-characterized clinical sample of individuals (n=1262) that had received detailed outpatient evaluation for the presence of an ASD diagnosis (n=481) and covered a range of additional differential or overlapping diagnoses, including anxiety related disorders (ANX, n=100), ADHD (n=440), and conduct disorder (CD, n=192). We focused on ADOS module 3, covering the age range with particular high prevalence of such differential diagnoses. We used machine learning (ML) and trained random forest models on ADOS single item scores to predict a clinical best estimate diagnosis of ASD in the context of these differential diagnoses (ASD vs. ANX, ASD vs. ADHD, ASD vs. CD) and an unspecific model using all available data. We employed nested cross-validation for an unbiased estimate of classification performance (ASD vs. non-ASD).ResultsWe obtained very good overall sensitivity (0.89-0.94) and specificity (0.87-0.89) for the classification of ASD vs. non-ASD. In particular for individuals with less severe symptoms (around the ADOS cut-off) our models showed increases of up to 20% in sensitivity or specificity. Furthermore, we analyzed item importance profiles of the ANX-, ADHD- and CD-models in comparison to the unspecific model. These analyses revealed distinct patterns of importance for specific ADOS-items with respect to differential diagnoses.ConclusionUsing ML-based diagnostic classification may improve clinical decisions by utilizing the full range of information from comprehensive and detailed diagnostic observation such as the ADOS. Importantly, this strategy might be of particular relevance for individuals with less severe symptoms that typically present a very difficult decision for the clinician.

show abstract

Temporal Behavioral Parameters of On-Going Gaze Encounters in a Virtual Environment

Cited by 8 publications

References 68 publications

Using machine learning to improve diagnostic assessment of ASD in the light of specific differential and co‐occurring diagnoses

Using machine learning to improve diagnostic assessment of ASD in the light of specific differential and co‐occurring diagnoses

Successful Modulation of Temporoparietal Junction Activity and Stimulus-Driven Attention by fNIRS-based Neurofeedback – a Randomized Controlled Proof-of-Concept Study

Using machine learning to improve diagnostic assessment of ASD in the light of specific differential diagnosis

Contact Info

Product

Resources

About